Release probing classifiers on Hugging Face

[NielsRogge]

Hi @ApaNC 🤗

I'm Niels and work as part of the open-source team at Hugging Face. I discovered your work through Hugging Face's daily papers as yours got featured: https://huggingface.co/papers/2602.12235.
The paper page lets people discuss about your paper and lets them find artifacts about it (your models for instance),
you can also claim the paper as yours which will show up on your public profile at HF, add Github and project page URLs.

I saw in the paper that you've developed lightweight probing classifiers to detect token overflow in soft-compressed representations, and that you've set up a GitHub repository at https://github.com/s-nlp/overflow-detection.

Would you like to host the pre-trained probing classifier checkpoints on https://huggingface.co/models once they are ready for release?
Hosting on Hugging Face will give your work more visibility and enable better discoverability. We can add metadata tags in the model cards so that people find the models easier and link them directly to the paper page.

If you're down, leaving a guide here. If these are custom PyTorch models, you can use the PyTorchModelHubMixin
class which adds from_pretrained and push_to_hub to the model, which lets you upload the model and allows people to download and use them right away.

Let me know if you're interested or need any guidance!

Kind regards,

Niels